Papers with CCA

12 papers
BERT is Not an Interlingua and the Bias of Tokenization (D19-61)

Copied to clipboard

Challenge: Cananical Correlation Analysis (CCA) of the internal representations of a pre- trained, multilingual BERT model reveals that the model partitions representations for each language rather than using a common, shared, interlingual space.
Approach: They propose to use a multilingual BERT model to partition representations for each language rather than using a common, shared, interlingual space.
Outcome: The results show that the model partitions representations for each language rather than using a common, shared, interlingual space.
Domain Adapted Word Embeddings for Improved Sentiment Classification (P18-2)

Copied to clipboard

Challenge: Generic word embeddings are trained on large-scale generic corpora, while domain specific ones are trained only on data from a domain of interest.
Approach: They propose a method to combine breadth of generic and specific embeddings to form domain-specific embeddables.
Outcome: The proposed method outperforms generic and domain specific embeddings on sentiment classification tasks.
Learning Word Embeddings for Data Sparse and Sentiment Rich Data Sets (N18-4)

Copied to clipboard

Challenge: Existing word embeddings for sentiment analysis are limited in domain specific applications . generic word embeds are poor initialization for tasks on domain specific data sets.
Approach: They propose to use word embeddings adapted for domain specific data sets in sentiment classification applications.
Outcome: The proposed algorithms learn word embeddings on sparse and sentiment rich data sets.
Situation-Based Multiparticipant Chat Summarization: a Concept, an Exploration-Annotation Tool and an Example Collection (2021.acl-srw)

Copied to clipboard

Challenge: Currently, text chat does not offer navigation or full-featured search, although the high volumes of messages demand it.
Approach: They propose a data annotation tool for situation-based summarization that can be used to extract messages from chat logs.
Outcome: The proposed tool is the first to be developed for situation-based summarization.
Cross-lingual Similarity of Multilingual Representations Revisited (2022.aacl-main)

Copied to clipboard

Challenge: Similarity indexes like CKA and CCA are not suitable for cross-lingual learning analysis.
Approach: They propose an alternative that is exempt from the difficulties of CKA/CCA and is good specifically in a cross-lingual context.
Outcome: The proposed method is exempt from the difficulties of CKA/CCA and is good specifically in a cross-lingual context.
Exploring the Value of Multi-View Learning for Session-Aware Query Representation (2022.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to learn distributed query representations only consider user’s query reformulations or system’s rankings . previous studies show that user’ s query behavior and knowledge change depending on the system’ 'results' and intertwine and affect each other during the completion of a search task.
Approach: They propose to use multi-view learning methods to align query embeddings with document ranking representations using transformers.
Outcome: The proposed approach can capture search intent semantics and can reflect user's query behavior and knowledge.
Ecco: An Open Source Library for the Explainability of Transformer Language Models (2021.acl-demo)

Copied to clipboard

Challenge: Existing models that use the Transformer architecture are lag behind our ability to scale them.
Approach: They propose an open-source library for the explainability of Transformer-based NLP models that captures, analyzes, visualizes, and interactively explores the inner mechanics of these models.
Outcome: The proposed tools capture, analyze, visualize, and explore the inner workings of Transformer-based language models.
Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer (2020.aacl-main)

Copied to clipboard

Challenge: Fine-tuning (FT) pre-trained sentence embedding models on small datasets has been shown to have limitations.
Approach: They propose to combine embeddings from a pre-trained model with a simple sentence embeddable model.
Outcome: The proposed approach outperforms FT on small datasets with negligible computational overhead.
MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting (2022.naacl-main)

Copied to clipboard

Challenge: Citation context analysis (CCA) is an important task in natural language processing that studies how and why scholars discuss each other’s work.
Approach: They propose to use a dataset of 12.6K citation contexts from 1.2K computational linguistics papers to model three important CCA phenomena.
Outcome: The proposed dataset contains 12.6K citation contexts from 1.2K computational linguistics papers and can model these phenomena.
Embedding Space Correlation as a Measure of Domain Similarity (2020.lrec-1)

Copied to clipboard

Challenge: Existing work on domain similarity using text-based features of corpus is limited by pre-trained word embeddings.
Approach: They propose a measure of domain similarity based on dimension-wise correlations between embedding spaces . they find a threshold at which the measure indicates that two corpora come from the same domain .
Outcome: The proposed measure can be used to determine which corpora are more similar to each other in a cross-domain sentiment detection task.
FineCite: A Novel Approach For Fine-Grained Citation Context Analysis (2025.findings-acl)

Copied to clipboard

Challenge: citation context analysis (CCA) studies the role and purpose of citations in scientific discourse.
Approach: They construct a first comprehensive context definition based on semantic properties of citing text . they use fine-grained semantic properties to evaluate the definition .
Outcome: The proposed definition shows improvements of up to 25% over state-of-the-art methods.
When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents (2026.acl-long)

Copied to clipboard

Challenge: Existing WebAgents suffer from computational cost attacks due to long reasoning processes and excessive computational cost.
Approach: They propose a framework that generates adversarial prompts and a reinforcement learning-enhanced selector to identify the most effective perturbations.
Outcome: The proposed framework exploits large language models to generate diverse adversarial prompts and a reinforcement learning–enhanced selector to identify the most effective perturbations.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations